Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/moniker.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import os.path
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     compat_urllib_parse,
  10     compat_urllib_request,
  11 )
  12
  13
  14 class MonikerIE(InfoExtractor):
  15     IE_DESC = 'allmyvideos.net and vidspot.net'
  16     _VALID_URL = r'https?://(?:www\.)?(?:allmyvideos|vidspot)\.net/(?P<id>[a-zA-Z0-9_-]+)'
  17
  18     _TESTS = [{
  19         'url': 'http://allmyvideos.net/jih3nce3x6wn',
  20         'md5': '710883dee1bfc370ecf9fa6a89307c88',
  21         'info_dict': {
  22             'id': 'jih3nce3x6wn',
  23             'ext': 'mp4',
  24             'title': 'youtube-dl test video',
  25         },
  26     }, {
  27         'url': 'http://vidspot.net/l2ngsmhs8ci5',
  28         'md5': '710883dee1bfc370ecf9fa6a89307c88',
  29         'info_dict': {
  30             'id': 'l2ngsmhs8ci5',
  31             'ext': 'mp4',
  32             'title': 'youtube-dl test video',
  33         },
  34     }, {
  35         'url': 'https://www.vidspot.net/l2ngsmhs8ci5',
  36         'only_matching': True,
  37     }]
  38
  39     def _real_extract(self, url):
  40         mobj = re.match(self._VALID_URL, url)
  41         video_id = mobj.group('id')
  42
  43         orig_webpage = self._download_webpage(url, video_id)
  44         fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage)
  45         data = dict(fields)
  46
  47         post = compat_urllib_parse.urlencode(data)
  48         headers = {
  49             b'Content-Type': b'application/x-www-form-urlencoded',
  50         }
  51         req = compat_urllib_request.Request(url, post, headers)
  52         webpage = self._download_webpage(
  53             req, video_id, note='Downloading video page ...')
  54
  55         title = os.path.splitext(data['fname'])[0]
  56
  57         #Could be several links with different quality
  58         links = re.findall(r'"file" : "?(.+?)",', webpage)
  59         # Assume the links are ordered in quality
  60         formats = [{
  61             'url': l,
  62             'quality': i,
  63         } for i, l in enumerate(links)]
  64         self._sort_formats(formats)
  65
  66         return {
  67             'id': video_id,
  68             'title': title,
  69             'formats': formats,
  70         }